{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:42Z","timestamp":1777889022444,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00025","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"187-196","source":"Crossref","is-referenced-by-count":0,"title":["One Object, Multiple Lies: A Benchmark for Cross-Task Adversarial Attack on Unified Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Jiale","family":"Zhao","sequence":"first","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyao","family":"Gao","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Xue","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cairong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Image hijacks: Adversarial images can control generative models at runtime","author":"Bailey","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19889"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102634"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02325"},{"key":"ref6","article-title":"How robust is google\u2019s bard to adversarial image attacks?","author":"Dong","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3349925"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26731"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3610614"},{"key":"ref10","article-title":"Faceshot: Bring any character into life","author":"Gao","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Ot-attack: Enhancing adversarial transferability of vision-language models via optimal transport optimization","author":"Han","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01659"},{"key":"ref13","article-title":"As firm as their foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2025.105321"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00264"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3592935"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"ref20","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.01.010"},{"key":"ref23","article-title":"An image is worth 1000 lies: Adversarial transferability across prompts on vision-language models","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.340"},{"key":"ref25","article-title":"Boosting cross-task transferability of adversarial patches with visual relations","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103257"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00395"},{"key":"ref30","article-title":"Unival: Unified model for image, video, audio and language tasks","author":"Shukor","year":"2023","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref31","article-title":"How many unicorns are in this image? a safety evaluation benchmark for vision llms","author":"Tu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Benchmarking zero-shot robustness of multimodal foundation models: A pilot study","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00102"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3106807"},{"key":"ref35","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681538"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650118"},{"key":"ref39","article-title":"X 2-vlm: All-in-one pretrained model for vision-language tasks","author":"Zeng","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref40","article-title":"Anyattack: Towards large-scale self-supervised generation of targeted adversarial examples for vision-language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/int.22932"},{"key":"ref42","article-title":"Benchmarking trustworthiness of multimodal large language models: A comprehensive study","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2355"},{"key":"ref44","article-title":"Adversarial attacks on hidden tasks in multitask learning","author":"Zhe","year":"2024","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443377.pdf?arnumber=11443377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:23Z","timestamp":1777611923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00025","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}